John Collison

It doesn't smell right.

So what actually turned out was happening is that our peripheral lighters bounced under the bus, and there was just a little bit of very, very noisy reflection of the movement of the person's feet.

That was enough for the AI models to say, hey, likely there's a pedestrian there, and I'm going to, you know, I detected a sign.

And moreover, there's enough data there to predict what they're going to do.

And it just kind of blew my mind.

I think it's an example where using that intermediate representation to boost the level of performance of all parts of the model is what's happening here.

Just imagine solving this problem with a black box, purely open loop, imitative system.

be, you know, impossible?

No.

In practice, what would it take to achieve that level of performance?

Yes.

Um,

We have about 3,000 cars on the roads.

We're doing about half a million rides per week.

That translates to about over 4 million fully autonomous miles per week.

Uh, we are operating in a fully autonomous mode in 11 cities, uh, in the US.

Uh, and 10 of those, uh, we have, uh, riders, you know, riders, uh, and... What's the ghost city?

The ghost city is Nashville.

So we just, uh, uh,

open it up to riders in four new cities in one day.